SYSTEMS AND METHODS FOR IDENTIFICATION DOCUMENT PROCESSING AND BUSINESS WORKFLOW INTEGRATION

• US 20150269433A1
• Filed: 03/19/2014
• Published: 09/24/2015
• Est. Priority Date: 01/12/2012
• Status: Active Grant

• Current Assignee: Kofax Incorporated
• Original Assignee: Kofax Incorporated
• Inventors: Amtrup, Jan W., Kilby, Steven, Macciola, Anthony
• Granted Patent: US 9,483,794 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 20/3223 Realising banking transactions through M-devices
• CPC Class Codes: G06Q 20/3276 using a pictured code, e.g. barcode or QR-code, being read by the M-device
• CPC Class Codes: G06Q 20/4014 Identity check for transactions
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof
• CPC Class Codes: G06Q 50/18 Legal services
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
• CPC Class Codes: G06V 30/416 Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
• CPC Class Codes: G06V 30/418 Document matching, e.g. of document images
• CPC Class Codes: H04N 1/00106 using land mobile radio networks, e.g. mobile telephone
• CPC Class Codes: H04N 1/00251 with an apparatus for taking photographic images, e.g. a camera
• CPC Class Codes: H04N 1/00334 with an apparatus processing barcodes or the like arrangements for sensing record carriers G06K7/00

Abstract

A method includes: capturing or receiving at least one image of one or more identity documents (IDs) using a mobile device; determining identifying information from one or more of the IDs; building an ID profile based on the identifying information; storing the ID profile to a memory of the mobile device; invoking a workflow configured to facilitate a business transaction; detecting a predetermined stimulus in the workflow, the stimulus relating to the business transaction; providing at least a portion of the ID profile to the workflow in response to detecting the predetermined stimulus; and driving at least a portion of the workflow using the provided portion of the ID profile. Related systems and computer program products are also disclosed.

Claims

1. A method, comprising

initiating a workflow;

receiving an image comprising a document;

analyzing the image to identify a plurality of document features, each document feature corresponding to the document;

building a feature vector based on at least some of the plurality of document features, wherein some or all of the plurality of document features upon which the feature vector is based comprise one or more image characteristics rather than textual information;

determining the document is an identity document (ID) based on the feature vector,

processing the image to generate data comprising one or more of;

identifying information from the ID; and

a portion of the image depicting the ID; and

submitting data to the workflow; and

driving at least a portion of the workflow using some or all of the data.

2. The method as recited in claim 1, the workflow further comprising:

detecting a predetermined stimulus in the workflow;

in response to detecting the predetermined stimulus, either;

invoking a capture interface of the workflow;

or

invoking a capture interface of a mobile device hosting at least a portion of the workflow; and

capturing the image using the invoked capture interface.

3. The method as recited in claim 1, wherein the ID is one of a plurality of IDs, and

wherein the data further comprises at least one of:

identifying information from at least two of the plurality of IDs; and

at least a portion of two or more of the plurality of IDs.

4. The method as recited in claim 1, wherein the feature vector describes a spatial distribution of the image characteristics as depicted in the image.

5. The method as recited in claim 1, wherein the feature vector describes a color profile of at least a portion of the image.

6. The method as recited in claim 1, further comprising building an ID profile based at least in part on the data;

storing the ID profile; and

performing the portion of the workflow at least in part using the ID profile.

7. The method as recited in claim 6, further comprising:

receiving one or more additional images comprising one or more additional identity documents (IDs);

processing the additional image(s) to generate additional data comprising at least one of

at least a portion of the one or more additional IDs; and

identifying information from one or more of the additional IDs; and

updating the ID profile based at least in part on the additional data.

8. The method as recited in claim 5, wherein the portion of the image depicts one or more of a photograph, a logo, an emblem, a seal, a hologram, and a watermark.

9. The method as recited in claim 6, further comprising verifying the ID profile.

10. The method as recited in claim 1, wherein the feature vector describes a spatial distribution of text fields as depicted in the image.

11. The method as recited in claim 6, wherein the ID profile comprises at least one ID identifier for each of the plurality of IDs.

12. The method as recited in claim 1, wherein the feature vector describes a spatial distribution of a plurality of lines as depicted in the image.

13. The method as recited in claim 1, wherein the image characteristics comprise one or more of

a line depicted on the document;

a pattern depicted on the document;

a border of the document;

a shape of an object depicted on the document; and

a color profile of one or more of the document and an object depicted on the document.

14. The method as recited in claim 6, wherein the ID profile comprises the feature vector.

15. The method as recited in claim 13, wherein the image characteristics comprise the color profile.

16. The method as recited in claim 13, wherein the image characteristics comprise the pattern, and

wherein the pattern comprises biometric data.

17. The method as recited in claim 1, wherein the ID comprises at least one multi-page document.

18. The method as recited in claim 17, wherein the multi-page document comprises at least a first page corresponding to a front side of the ID and a second page corresponding to a back side of the ID.

19. The method as recited in claim 2, wherein the workflow comprises

a tracking activity, wherein the predetermined stimulus comprises one or more of:

invoking an authentication interface; and

invoking a logout interface.

20. The method as recited in claim 13, wherein the image characteristics comprise the pattern, and

wherein the pattern comprises a distribution of one or more of:

lines depicted in the document

borders depicted in the document; and

boxes depicted in the document.

30. The method as recited in claim 1, wherein determining the document is an identity document (ID) comprises a support-vector machine technique.

21. A method, comprising:

capturing or receiving at least one image of one or more documents using a mobile device;

determining at least one of the documents is an identity document (ID) at least in part using support-vector machine techniques, wherein determining the at least one of the documents is an ID comprises;

analyzing the image to identify a plurality of document features, each document feature corresponding to the document;

building a feature vector based on at least some of the plurality of document features; and

determining the document is an identity document (ID) based on the feature vector, wherein some or all of the plurality of document features upon which the feature vector is based comprise one or more image characteristics rather than textual information;

determining identifying information from one or more of the IDs;

building an ID profile based on the identifying information;

storing the ID profile to a memory of the mobile device;

invoking a workflow configured to facilitate a business transaction;

detecting a predetermined stimulus in the workflow, the stimulus relating to the business transaction;

providing at least a portion of the ID profile to the workflow in response to detecting the predetermined stimulus; and

driving at least a portion of the workflow using the provided portion of the ID profile.

27. The method as recited in claim 21, further comprising

analyzing the image to identify a plurality of document features, each document feature corresponding to the document;

building a feature vector based on at least some of the plurality of document features; and

determining the document is an identity document (ID) based on the feature vector.

22. A computer program product, comprising:

a non-transitory computer readable storage medium having computer readable program code stored therein, the computer readable program code comprising instructions configured to cause a processor to;

capture or receive at least one image of one or more identity documents (IDs) using a mobile device;

determine identifying information from the one or more IDs based at least in part on;

analyzing the image to identify a plurality of document features, each document feature corresponding to the document;

building a feature vector based on at least some of the plurality of document features; and

determining the document is an identity document (ID) based on the feature vector, wherein some or all of the plurality of document features upon which the feature vector is based comprise one or more image characteristics rather than textual information;

build an ID profile based on the identifying information;

associate at least some of the identifying information with the image as metadata;

store the ID profile to a memory of the mobile device;

store the image and the associated metadata to the memory of the mobile device;

invoke a workflow configured to facilitate a business transaction;

detect a predetermined stimulus relating to the business transaction;

provide at least a portion of the ID profile to the workflow in response to detecting the predetermined stimulus; and

facilitate the business transaction using the provided portion of the ID profile.

23. The computer program product as recited in claim 22,

wherein the business transaction comprises a driver'"'"'s license renewal, and

wherein the predetermined stimulus comprises one or more of:

existence of a hold on the driver'"'"'s license renewal;

nonexistence of any hold(s) on the driver'"'"'s license renewal.

24. The computer program product as recited in claim 22, wherein facilitating the business transaction comprises one or more of:

invoking a driver license renewal interface in response to detecting the nonexistence of any hold(s) n the driver'"'"'s license renewal;

invoking a fee payment submission interface in response to detecting the existence of a fee-related hold on the driver'"'"'s license renewal;

invoking a driver education application interface in response to detecting the existence of either a hold relating to one or more traffic violations or a hold relating to a judgment.

25. The computer program product as recited in claim 24, wherein the business transaction comprises a tax return,

wherein the predetermined stimulus comprises a request from the workflow for tax information;

and

wherein facilitating the business transaction comprises one or more of;

determining whether the tax return is eligible for one or more of deductions or credits;

retrieving the tax information using a lookup process based on identifying information depicted on the one or more IDs; and

populating a standard tax form with the tax information.

26. The computer program product as recited in claim 22, wherein, the ID profile comprises a feature vector descriptive of image characteristics rather than textual information.

28. The computer program product as recited in claim 22,

further comprising instructions configured to cause the processor to:

analyze the image to identify a plurality of document features, each document feature corresponding to the document;

build a feature vector based on at least some of the plurality of document features; and

determine the document is an identity document (ID) based on the feature vector, and

wherein some or all of the plurality of document features upon which the feature vector is based comprise one or more image characteristics rather than textual information.

29. The computer program product as recited in claim 22, wherein determining the document is an identity document (ID) comprises a support-vector machine technique.